AgriChrono: A Multi-modal Dataset Capturing Crop Growth and Lighting Variability with a Field Robot

2025-08-26

AI Summary

Existing agricultural datasets are predominantly collected in static, controlled environments using single-modality sensors and short temporal sequences, failing to capture real-world field dynamics—including diurnal illumination variations, crop growth progression, and natural disturbances—thereby limiting model generalizability. To address this, we introduce the first multimodal, long-term dataset specifically designed for dynamic outdoor farmland. Acquired via an autonomous field robot, it synchronously captures RGB, depth, LiDAR, and IMU data across full daylight cycles and complete crop growth stages. The platform enables remote operation, sub-millisecond hardware time synchronization, and repeatable field deployments, and includes a standardized 3D reconstruction benchmark. Both dataset and code are publicly released. Experimental evaluation reveals substantial performance degradation of state-of-the-art 3D reconstruction models under real-field conditions, empirically validating the dataset’s critical role in advancing robustness and generalization of agricultural perception systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Existing datasets for precision agriculture have primarily been collected in static or controlled environments such as indoor labs or greenhouses, often with limited sensor diversity and restricted temporal span. These conditions fail to reflect the dynamic nature of real farmland, including illumination changes, crop growth variation, and natural disturbances. As a result, models trained on such data often lack robustness and generalization when applied to real-world field scenarios. In this paper, we present AgriChrono, a novel robotic data collection platform and multi-modal dataset designed to capture the dynamic conditions of real-world agricultural environments. Our platform integrates multiple sensors and enables remote, time-synchronized acquisition of RGB, Depth, LiDAR, and IMU data, supporting efficient and repeatable long-term data collection across varying illumination and crop growth stages. We benchmark a range of state-of-the-art 3D reconstruction models on the AgriChrono dataset, highlighting the difficulty of reconstruction in real-world field environments and demonstrating its value as a research asset for advancing model generalization under dynamic conditions. The code and dataset are publicly available at: https://github.com/StructuresComp/agri-chrono

Problem

• Captures dynamic crop growth and lighting variability
• Addresses limited sensor diversity in agricultural datasets
• Improves model robustness for real-world field conditions

Innovation

• Robotic platform for multi-sensor data collection
• Time-synchronized RGB, Depth, LiDAR, IMU acquisition
• Long-term monitoring across illumination and growth stages